English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Paper

Content-Based Weak Supervision for Ad-Hoc Re-Ranking

MPS-Authors
/persons/resource/persons206666

Yates,  Andrew
Databases and Information Systems, MPI for Informatics, Max Planck Society;

External Ressource
No external resources are shared
Fulltext (public)

arXiv:1707.00189.pdf
(Preprint), 138KB

Supplementary Material (public)
There is no public supplementary material available
Citation

MacAvaney, S., Yates, A., Hui, K., & Frieder, O. (2019). Content-Based Weak Supervision for Ad-Hoc Re-Ranking. Retrieved from http://arxiv.org/abs/1707.00189.


Cite as: http://hdl.handle.net/21.11116/0000-0005-6B59-0
Abstract
One challenge with neural ranking is the need for a large amount of manually-labeled relevance judgments for training. In contrast with prior work, we examine the use of weak supervision sources for training that yield pseudo query-document pairs that already exhibit relevance (e.g., newswire headline-content pairs and encyclopedic heading-paragraph pairs). We also propose filtering techniques to eliminate training samples that are too far out of domain using two techniques: a heuristic-based approach and novel supervised filter that re-purposes a neural ranker. Using several leading neural ranking architectures and multiple weak supervision datasets, we show that these sources of training pairs are effective on their own (outperforming prior weak supervision techniques), and that filtering can further improve performance.